Properties of combinations of hierarchical watersheds

Autor: Deise Santana Maia, Laurent Najman, Jean Cousty, Benjamin Perret
Přispěvatelé: Laboratoire d'Informatique Gaspard-Monge (LIGM), Centre National de la Recherche Scientifique (CNRS)-Fédération de Recherche Bézout-ESIEE Paris-École des Ponts ParisTech (ENPC)-Université Paris-Est Marne-la-Vallée (UPEM), Laboratoire des Sciences de l'Image, de l'Informatique et de la Télédétection (LSIIT), Centre National de la Recherche Scientifique (CNRS), Laboratoire d'Informatique Gaspard-Monge (ligm), Université Paris-Est Marne-la-Vallée (UPEM)-École des Ponts ParisTech (ENPC)-ESIEE Paris-Fédération de Recherche Bézout-Centre National de la Recherche Scientifique (CNRS)
Rok vydání: 2019
Předmět:
Zdroj: Pattern Recognition Letters
Pattern Recognition Letters, Elsevier, 2019, 128, pp.513-520. ⟨10.1016/j.patrec.2019.10.009⟩
ISSN: 0167-8655
DOI: 10.1016/j.patrec.2019.10.009
Popis: International audience; In [12], the authors provide an evaluation of combinations of hierarchical watersheds, showing that some combinations outperform individual hierarchical watersheds. In this article, we aim to achieve a deeper understanding of those combinations. We study which of the four combinations evaluated in [12] always result in flattened (simplified) hierarchical watersheds. Then, we provide a sufficient condition for a combination to always output flattened hierarchical watersheds, and a new combining function that outputs flattened hierarchical watersheds. We conclude that, among the combinations assessed in [12], only a particular case of combinations with infimum always result in flattened hierarchical watersheds.
Databáze: OpenAIRE